Live / Together AI / Incident
Together AI: GCP Infrastructure Outage Impacting Together Platform
Together AI · together.aiCritical outageResolved2025-06-12 21:17 UTC
Public — what happened
Summary
Together AI reported a critical outage beginning at 18:31 UTC on June 12, 2025, that took down its entire platform, including signing in, ongoing sessions and general access to the app. The company attributed the problem to a large-scale infrastructure failure at its cloud provider, Google Cloud Platform. By 20:04 UTC it said the main application was working again, though some secondary features could remain unreliable while Google finished its repairs. Together AI marked the incident resolved at 21:17 UTC.
Affected
Web Hosting
Timeline
- Started — 2025-06-12 18:31 UTC
- Identified — 2025-06-12 18:31 UTC (2 updates)
- Resolved — 2025-06-12 21:17 UTC · 2h 46m after it started
With SquidGrid — where it starts on the route
Independent path health
The status page is the symptom. SquidGrid measures the paths that reach Together AI against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.
🔒 Sign in to seeCustomers get the live Provider Assessment Report for Together AI: its full incident track record, what tends to break, and recent public reports of problems.
Included with any paid plan.
Open the Together AI report →
More from Together AI